Test Rphenograph clustering Jan 25 2022

Load libraries - see what is needed as I go

library(FlowSOM)

Loading required package: igraph
Warning: package ‘igraph’ was built under R version 4.1.2

Attaching package: ‘igraph’

The following objects are masked from ‘package:stats’:

    decompose, spectrum

The following object is masked from ‘package:base’:

    union

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Thanks for using FlowSOM. From version 2.1.4 on, the scale 
parameter in the FlowSOM function defaults to FALSE

#library(flowCore)
#library(cluster)
#library(fpc)
#library(clv)
library(Seurat)

Warning: package ‘Seurat’ was built under R version 4.1.2
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio
Registered S3 method overwritten by 'spatstat.geom':
  method     from
  print.boxx cli 
Attaching SeuratObject

library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:igraph’:

    as_data_frame, groups, union

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(Rphenograph)

Loading required package: ggplot2

rm(list=ls())

Code from website to test installation and to figure out how the inputs work.

membership(Rphenograph_out[[2]])

  1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21  22  23  24  25  26  27  28 
  1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1 
 29  30  31  32  33  34  35  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53  54  55  56 
  1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   1   2   2   2   2   2   2 
 57  58  59  60  61  62  63  64  65  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83  84 
  2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2 
 85  86  87  88  89  90  91  92  93  94  95  96  97  98  99 100 101 102 103 104 105 106 107 108 109 110 111 112 
  2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   2   3   2   3   3   3   3   2   3   3   3   3   3 
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 
  3   2   3   3   3   3   3   2   3   2   3   2   3   3   2   2   3   3   3   3   3   2   3   3   3   3   2   3 
141 142 143 144 145 146 147 148 149 
  3   3   3   3   3   2   3   3   2 

The phenograph example works - Apply to the flow data

# read in the data and create an expression matrix 

#input file path, change if needed
fileName <-"/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/prepro_outsflowset.csv"

# note: current matrix sample ID have cell index # attached. 

df <- read.csv(fileName)
head(df)

print(dim(df)) # this is specific df has 73578 cells

[1] 73578    19

# the preprocessing output csv needs to be cleaned - it contains live dead, FSC, SSC and the sample column
df2 <- df %>% select(-c("Live.Dead",FSC,SSC,X,Batch,cell))

m <- as.matrix(df2) # make a matrix as input to phenograph

unique(df$phenograph_cluster)

 [1] 1  2  3  4  5  6  7  8  9  10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
Levels: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30

Try with a higher k

# Rphenograph seems to be just one function and we can adjust the K for number of neighbours
Rphenograph_out_flow <- Rphenograph(m, k = 271)

Run Rphenograph starts:
  -Input data of 73578 rows and 13 columns
  -k is set to 271

  Finding nearest neighbors...DONE ~ 25.11 s
  Compute jaccard coefficient between nearest-neighbor sets...DONE ~ 1747.534 s
  Build undirected graph from the weighted links...DONE ~ 101.951 s
  Run louvain clustering on the graph ...DONE ~ 87.838 s

Run Rphenograph DONE, totally takes 1962.433s.

  Return a community class
  -Modularity value: 0.825605 
  -Number of clusters: 22

modularity(Rphenograph_out_flow[[2]])

[1] 0.825605

membership(Rphenograph_out_flow[[2]])

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16   17   18   19   20   21   22 
   1    2    2    2    3    4    5    4    6    3    7    8    9    2   10   11    1   12    2   13   12    5 
  23   24   25   26   27   28   29   30   31   32   33   34   35   36   37   38   39   40   41   42   43   44 
  13   14   12   15    9    3    3    3   15    3    8    3   15    9    3    3    3    8   11    1    9   11 
  45   46   47   48   49   50   51   52   53   54   55   56   57   58   59   60   61   62   63   64   65   66 
   9   13    9   15    9   13    5    7   16   13    3   17   16    4    2    5   15    2   15    5   16    1 
  67   68   69   70   71   72   73   74   75   76   77   78   79   80   81   82   83   84   85   86   87   88 
   9    9   13    9    9   18   13    5    8    5    6   18    6    7    2    1    1    7    9   13   13    3 
  89   90   91   92   93   94   95   96   97   98   99  100  101  102  103  104  105  106  107  108  109  110 
   8   17    8    8    3    9   13   13    2   17   19    7   15    9    9    3    8    3    5   15    5   13 
 111  112  113  114  115  116  117  118  119  120  121  122  123  124  125  126  127  128  129  130  131  132 
   8   13   16    2    3    1   16   13    4   13    9    4    9    8   13    3   18    8    4   15    1    4 
 133  134  135  136  137  138  139  140  141  142  143  144  145  146  147  148  149  150  151  152  153  154 
   2   18   15    9   17    1    3   16    1    1    2   13   13   13    3    8    2   16   14    9   16    3 
 155  156  157  158  159  160  161  162  163  164  165  166  167  168  169  170  171  172  173  174  175  176 
  13   16   13   12    2   13   11    8   13   18    4    8    1    8    7   16    4   13    9    5   15    9 
 177  178  179  180  181  182  183  184  185  186  187  188  189  190  191  192  193  194  195  196  197  198 
  13   15    3    3    9    3   15    8    4    6    8    3   15    2   13   11   15   20    5    5   17   18 
 199  200  201  202  203  204  205  206  207  208  209  210  211  212  213  214  215  216  217  218  219  220 
   8   15    3    9   18    3    7    5    2    3    8   13   21    8    1    3    9   17    4    3   13    8 
 221  222  223  224  225  226  227  228  229  230  231  232  233  234  235  236  237  238  239  240  241  242 
   6    3    9    3    9   18    8   18    1    8   13   13    7   13    2    1    1    7    1    9    5    8 
 243  244  245  246  247  248  249  250  251  252  253  254  255  256  257  258  259  260  261  262  263  264 
  13    5    8   16    5   15    1   13    1    9    1    8    3    6   15   20    8   13    3   17   15    9 
 265  266  267  268  269  270  271  272  273  274  275  276  277  278  279  280  281  282  283  284  285  286 
  13    3   13   15    9    9    2   13    3    8    9   15   13    7    7   13   15   15    9    4    8   15 
 287  288  289  290  291  292  293  294  295  296  297  298  299  300  301  302  303  304  305  306  307  308 
   3    2    3    9    5    8    9    3    9    8    1    6    7    3    7    8    5   18    8    6   13   17 
 309  310  311  312  313  314  315  316  317  318  319  320  321  322  323  324  325  326  327  328  329  330 
   1    9    9   13   13    8    9   13    9   15   11    9   16    7    5 0.826    4   16    7    3    9    9 
 331  332  333  334  335  336  337  338  339  340  341  342  343  344  345  346  347  348  349  350  351  352 
   4    3    6   16   17   13   15    8    2   21   19   16   13   13   13   13    4    3   17    5    2    9 
 353  354  355  356  357  358  359  360  361  362  363  364  365  366  367  368  369  370  371  372  373  374 
  12   14   10    2    3   13    8    8    7   13   20   13    3   10    3   13    7    1   13   10   13    7 
 375  376  377  378  379  380  381  382  383  384  385  386  387  388  389  390  391  392  393  394  395  396 
  13   15    3    3   16    1   11    9   17    1   16    9    9   15    2   13   21   13    9   16   15   15 
 397  398  399  400  401  402  403  404  405  406  407  408  409  410  411  412  413  414  415  416  417  418 
  15    2    2    6    1   13   11    8    8    1    1    2   13   10    9    2    3   13   18    2   13   15 
 419  420  421  422  423  424  425  426  427  428  429  430  431  432  433  434  435  436  437  438  439  440 
   3    7   13   13    3    7   13   21   18   13    8   13    2    7    2    7   16   13    9    4   16   12 
 441  442  443  444  445  446  447  448  449  450  451  452  453  454  455  456  457  458  459  460  461  462 
  20   13    1    3   16   15   13    7   16    3    8    9    7    8    8   13   18   16   16    8    7   20 
 463  464  465  466  467  468  469  470  471  472  473  474  475  476  477  478  479  480  481  482  483  484 
   9    1    3    8    8    7    8    5    6   10    7   15    5    5   13    1    1    1    3   11   13    5 
 485  486  487  488  489  490  491  492  493  494  495  496  497  498  499  500  501  502  503  504  505  506 
   9    8    1    8   15   17    8    8    3   13    8   16   17    3   18    2    9   18    1   13    4    8 
 507  508  509  510  511  512  513  514  515  516  517  518  519  520  521  522  523  524  525  526  527  528 
   7    8    9    9   13   15    2    8    1   18    1   17    7    1   10   20   18    8    7    4   16   15 
 529  530  531  532  533  534  535  536  537  538  539  540  541  542  543  544  545  546  547  548  549  550 
   3   15   14   13    3    3    4    8   13   15    8    2   18   13    5   13    8   15   16    1   11    9 
 551  552  553  554  555  556  557  558  559  560  561  562  563  564  565  566  567  568  569  570  571  572 
  15   13    9    1   17    8    8    6    1   13    4    2    8   15    3   15    5   15   17    2   16   11 
 573  574  575  576  577  578  579  580  581  582  583  584  585  586  587  588  589  590  591  592  593  594 
   8   15    7    7   13    1    5    1   13   11   13   18    1    7   13    9   11    8    1    3   21   16 
 595  596  597  598  599  600  601  602  603  604  605  606  607  608  609  610  611  612  613  614  615  616 
   2   15    8   13   18    9    1    1    2    4   15    8    5    3    1   16    7    5   13   16   15   13 
 617  618  619  620  621  622  623  624  625  626  627  628  629  630  631  632  633  634  635  636  637  638 
   4    1    3    8    3    3   13    9    8    2   10    8   13    1   17    4   15   15    8    8    1   15 
 639  640  641  642  643  644  645  646  647  648  649  650  651  652  653  654  655  656  657  658  659  660 
   6    3    9    5    8    9    1   17    3    8    5   15   13   13    4    9   13   13   13    4    5   11 
 661  662  663  664  665  666  667  668  669  670  671  672  673  674  675  676  677  678  679  680  681  682 
   9    2   16    8   13   13    9    3    9    3   15    2    9   15    8    3    1   13    8    8   17    5 
 683  684  685  686  687  688  689  690  691  692  693  694  695  696  697  698  699  700  701  702  703  704 
   1    5   13   16   18    4   16    1   16   11   16   13    9   13    7    3   13   17    7   15    2    6 
 705  706  707  708  709  710  711  712  713  714  715  716  717  718  719  720  721  722  723  724  725  726 
  10    7    5    8    4    8   11    8   13    8   18    1    8    1    3    6   15    1    3    8   11   13 
 727  728  729  730  731  732  733  734  735  736  737  738  739  740  741  742  743  744  745  746  747  748 
  13    8   13   18    8   13    6   13    2    7    1   15    5   17    8    5    7    9    8   14    3    3 
 749  750  751  752  753  754  755  756  757  758  759  760  761  762  763  764  765  766  767  768  769  770 
   3   17   13    5    5   17    8    8    2   15   16    5    9    4   15   17    1    8   15   15    8   17 
 771  772  773  774  775  776  777  778  779  780  781  782  783  784  785  786  787  788  789  790  791  792 
   8    5   15   13   15    9   13    1    2    3   20    8    3    8   16    5    6   13    2   14   13   20 
 793  794  795  796  797  798  799  800  801  802  803  804  805  806  807  808  809  810  811  812  813  814 
   1    4   15    5   20    2    3    8    8   18    9   20    8    6    8   16    6    1   15    9    5    7 
 815  816  817  818  819  820  821  822  823  824  825  826  827  828  829  830  831  832  833  834  835  836 
   3    3    8    3    9   20    5   18    3    3    1    9   13   14    7    5    9    2   17    4    3   11 
 837  838  839  840  841  842  843  844  845  846  847  848  849  850  851  852  853  854  855  856  857  858 
   8    7    5   12    1   15   15   11    8   15    1    7    9    8    4    9    3    3   20    5    2    5 
 859  860  861  862  863  864  865  866  867  868  869  870  871  872  873  874  875  876  877  878  879  880 
  15    1   13    7   16   11   13    2    7    4    9   10   21    3   13   15    1    7    9   13    2    1 
 881  882  883  884  885  886  887  888  889  890  891  892  893  894  895  896  897  898  899  900  901  902 
  13    2    8    3    1   13   13   19   15   13    9    1    2    5   13   13   13    9    9    3   20    3 
 903  904  905  906  907  908  909  910  911  912  913  914  915  916  917  918  919  920  921  922  923  924 
  15    8    7    8   15   13   13   10    3    4   13    8    8    6   18   11   13    1   13   18    4    2 
 925  926  927  928  929  930  931  932  933  934  935  936  937  938  939  940  941  942  943  944  945  946 
   7    8    3    3   16   21   11    9    3    1    6    8   11   20    5    9   15   11    4    3    4   13 
 947  948  949  950  951  952  953  954  955  956  957  958  959  960  961  962  963  964  965  966  967  968 
   4    8    8    3    3   18   13    1    1   10   18    8    9    8    1   18   13    8    8    9   13   15 
 969  970  971  972  973  974  975  976  977  978  979  980  981  982  983  984  985  986  987  988  989  990 
  15   21    8    3   13   17   14    5    8   13    8   10   18    7   17    7    3    4   13   21   14    1 
 991  992  993  994  995  996  997  998  999 1000 
  14    2   13    5    9    8    2    1    7    9 
 [ reached getOption("max.print") -- omitted 72578 entries ]

# add cluster ID back into original df
df$phenograph_clusterk271 <- factor(membership(Rphenograph_out_flow[[2]]))

# how many clusters are there?
unique(df$phenograph_cluster)

 [1] 1  2  3  4  5  6  7  8  9  10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
Levels: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30

# 30 levels !!!! Way to many - because the k is low. 

#ggplot(iris_unique, aes(x=Sepal.Length, y=Sepal.Width, col=Species, shape=phenograph_cluster)) + geom_point(size = 3)+theme_bw()

# how many clusters are there?
unique(df$phenograph_clusterk271)

 [1] 1  2  3  4  5  6  7  8  9  10 11 12 13 14 15 16 17 18 19 20 21 22
Levels: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22

# I'll have a look at the clustering quickly using two AB


ggplot(df, aes(x=CD44, y=CD71, col = phenograph_clusterk271)) + geom_point(size = 1)+theme_bw()

Save the df with the phenograph cluster indexes to save time.

write.csv(df,"/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/prepro_outsflowsetdf+phenographk50k271.csv")

# seurat object made from the save input as the phenograph clustering
seu <- readRDS("/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/SeuratfromFlowsom.rds")

# read in the df with the phenograph clustering
df <- read.csv("/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/prepro_outsflowsetdf+phenographk50k271.csv")

# add the phenograph cluster indexes
seu <- AddMetaData(object=seu, metadata=df$phenograph_clusterk271, col.name = 'Phenograph.k.271')

See some plots

DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "Phenograph.k.271")

NA
NA

# make a list of AB from the input df - can only use df if filter out all the exta parts
print(colnames(df2))

 [1] "AQP4"    "CD56"    "GLAST"   "CD140a"  "CD29"    "CD44"    "CD184"   "CD71"    "CD24"    "CD15"   
[11] "O4"      "HepaCAM" "CD133"  

allAB <- colnames(df2)

DoHeatmap(seu, features = allAB, group.by = "Phenograph.k.271")

DotPlot(seu, features = allAB, group.by = "Phenograph.k.271", cols = c("blue","red"))

DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "flowSOM.k.8")

DoHeatmap(seu, features = allAB, group.by = "flowSOM.k.8")

NA
NA

Save seurat object with Phenograph and FlowSOM.k.8 clusters

saveRDS(seu,"/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/SeuratfromFlowsomPheno.rds" )

Try to optimize UMAP to get better separation of groups

spread.opt <- c(0.1,0.5,0.75,1,5)
a.opt <- c(830,5.07,2.51,1.58,0.14)
b.opt <- c(1.93,1.0,0.93,0.90,0.81)

for (i in 1:5){
  seu <- RunUMAP(seu, dims = NULL, n.neighbors = 250, min.dist = 0.1 ,features = allAB, slot = 'scale.data', spread = spread.opt[i], a = a.opt[i], b = b.opt[i])
  print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "Phenograph.k.271"))
  print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.1"))
}

16:11:05 Read 73578 rows and found 13 numeric columns
16:11:05 Using Annoy for neighbor search, n_neighbors = 250
16:11:05 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:11:11 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da11ca0b4c2
16:11:11 Searching Annoy index using 1 thread, search_k = 25000
16:13:27 Annoy recall = 100%
16:13:28 Commencing smooth kNN distance calibration using 1 thread
16:13:55 Initializing from normalized Laplacian + noise
16:14:50 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:16:11 Optimization finished
16:16:15 Read 73578 rows and found 13 numeric columns
16:16:15 Using Annoy for neighbor search, n_neighbors = 250
16:16:15 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:16:20 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da17abb3b3c
16:16:20 Searching Annoy index using 1 thread, search_k = 25000
16:18:36 Annoy recall = 100%
16:18:36 Commencing smooth kNN distance calibration using 1 thread
16:19:04 Initializing from normalized Laplacian + noise
16:19:58 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:21:19 Optimization finished
16:21:22 Read 73578 rows and found 13 numeric columns
16:21:22 Using Annoy for neighbor search, n_neighbors = 250
16:21:22 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:21:27 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da11a2e1f17
16:21:27 Searching Annoy index using 1 thread, search_k = 25000
16:28:56 Annoy recall = 100%
16:28:57 Commencing smooth kNN distance calibration using 1 thread
16:29:24 Initializing from normalized Laplacian + noise
16:30:19 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:31:40 Optimization finished
16:31:43 Read 73578 rows and found 13 numeric columns
16:31:43 Using Annoy for neighbor search, n_neighbors = 250
16:31:43 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:31:48 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da149fb2c6e
16:31:48 Searching Annoy index using 1 thread, search_k = 25000
16:34:06 Annoy recall = 100%
16:34:07 Commencing smooth kNN distance calibration using 1 thread
16:34:36 Initializing from normalized Laplacian + noise
16:35:32 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:36:53 Optimization finished
16:36:57 Read 73578 rows and found 13 numeric columns
16:36:57 Using Annoy for neighbor search, n_neighbors = 250
16:36:57 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:37:02 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da19220fb4
16:37:02 Searching Annoy index using 1 thread, search_k = 25000
16:39:21 Annoy recall = 100%
16:39:21 Commencing smooth kNN distance calibration using 1 thread
16:39:49 Initializing from normalized Laplacian + noise
16:40:44 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:42:06 Optimization finished

resolutions = c("RNA_snn_res.0.1","RNA_snn_res.0.25","RNA_snn_res.0.5","RNA_snn_res.0.75","RNA_snn_res.1")

for (res in resolutions){
 print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = res))
 
}

NA
NA

# run at a higher spread
seu2 <- seu

seu2 <- RunUMAP(seu2, dims = NULL, n.neighbors = 250, min.dist = 0.01 ,features = allAB, slot = 'scale.data', spread =10, a = 0.05, b = 0.8)

16:50:47 Read 73578 rows and found 13 numeric columns
16:50:47 Using Annoy for neighbor search, n_neighbors = 250
16:50:47 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:50:52 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da152d749e1
16:50:52 Searching Annoy index using 1 thread, search_k = 25000
16:53:06 Annoy recall = 100%
16:53:07 Commencing smooth kNN distance calibration using 1 thread
16:53:35 Initializing from normalized Laplacian + noise
16:54:30 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
16:55:51 Optimization finished

resolutions = c("RNA_snn_res.0.1","RNA_snn_res.0.25","RNA_snn_res.0.5","RNA_snn_res.0.75","RNA_snn_res.1")

for (res in resolutions){
 print(DimPlot(seu2, reduction = "umap", repel = TRUE, label = TRUE, group.by = res))
 
}

DimPlot(seu2, reduction = "umap", repel = TRUE, label = TRUE, group.by = "Phenograph.k.271")

NA
NA
NA

seu3 <- seu

spread.opt <- c(2,3,5)
a.opt <- c(0.54,0.3,0.14)
b.opt <- c(0.84,0.82,0.81)

for (i in 1:5){
  seu <- RunUMAP(seu, dims = NULL, n.neighbors = 250, min.dist = 0.001 ,features = allAB, slot = 'scale.data', spread = spread.opt[i], a = a.opt[i], b = b.opt[i])
  print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "Phenograph.k.271"))
  print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.1"))
}

17:05:04 Read 73578 rows and found 13 numeric columns
17:05:04 Using Annoy for neighbor search, n_neighbors = 250
17:05:04 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:05:09 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da134337d44
17:05:09 Searching Annoy index using 1 thread, search_k = 25000
17:07:23 Annoy recall = 100%
17:07:24 Commencing smooth kNN distance calibration using 1 thread
17:07:51 Initializing from normalized Laplacian + noise
17:08:47 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:10:08 Optimization finished
17:10:11 Read 73578 rows and found 13 numeric columns
17:10:11 Using Annoy for neighbor search, n_neighbors = 250
17:10:11 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:10:16 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da120651622
17:10:16 Searching Annoy index using 1 thread, search_k = 25000
17:12:29 Annoy recall = 100%
17:12:29 Commencing smooth kNN distance calibration using 1 thread
17:12:57 Initializing from normalized Laplacian + noise
17:13:51 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:15:12 Optimization finished
17:15:15 Read 73578 rows and found 13 numeric columns
17:15:15 Using Annoy for neighbor search, n_neighbors = 250
17:15:15 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:15:21 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da14c9022cb
17:15:21 Searching Annoy index using 1 thread, search_k = 25000
17:17:34 Annoy recall = 100%
17:17:34 Commencing smooth kNN distance calibration using 1 thread
17:18:02 Initializing from normalized Laplacian + noise
17:18:57 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:20:18 Optimization finished
17:20:22 Read 73578 rows and found 13 numeric columns
17:20:22 Using Annoy for neighbor search, n_neighbors = 250
17:20:22 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:20:27 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da1adc64b2
17:20:27 Searching Annoy index using 1 thread, search_k = 25000
17:22:42 Annoy recall = 100%
17:22:43 Commencing smooth kNN distance calibration using 1 thread
17:23:11 Initializing from normalized Laplacian + noise
17:24:06 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:24:48 Optimization finished
Warning: Removed 73578 rows containing missing values (geom_point).
Warning: Removed 22 rows containing missing values (geom_text_repel).
Warning: Removed 73578 rows containing missing values (geom_point).
Warning: Removed 15 rows containing missing values (geom_text_repel).
17:24:49 Read 73578 rows and found 13 numeric columns
17:24:49 Using Annoy for neighbor search, n_neighbors = 250
17:24:49 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:24:54 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da1b56e7b0
17:24:55 Searching Annoy index using 1 thread, search_k = 25000
17:27:17 Annoy recall = 100%
17:27:17 Commencing smooth kNN distance calibration using 1 thread
17:27:46 Initializing from normalized Laplacian + noise
17:28:41 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
17:29:23 Optimization finished
Warning: Removed 73578 rows containing missing values (geom_point).
Warning: Removed 22 rows containing missing values (geom_text_repel).
Warning: Removed 73578 rows containing missing values (geom_point).
Warning: Removed 15 rows containing missing values (geom_text_repel).

# spread 3 

dist.opt = c(0.001,0.005,0.01,0.05)

for (ds in dist.opt){
  seu <- RunUMAP(seu, dims = NULL, n.neighbors = 250, min.dist = ds ,features = allAB, slot = 'scale.data', spread = 3, a = 0.3, b = 0.82)
  print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "Phenograph.k.271"))
  print(DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.1"))
}

10:29:35 Read 73578 rows and found 13 numeric columns
10:29:35 Using Annoy for neighbor search, n_neighbors = 250
10:29:35 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:29:40 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da1176ac32d
10:29:40 Searching Annoy index using 1 thread, search_k = 25000
10:31:56 Annoy recall = 100%
10:31:57 Commencing smooth kNN distance calibration using 1 thread
10:32:26 Initializing from normalized Laplacian + noise
10:33:22 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:34:42 Optimization finished
10:34:46 Read 73578 rows and found 13 numeric columns
10:34:46 Using Annoy for neighbor search, n_neighbors = 250
10:34:46 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:34:51 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da16233cb5d
10:34:51 Searching Annoy index using 1 thread, search_k = 25000
10:37:07 Annoy recall = 100%
10:37:08 Commencing smooth kNN distance calibration using 1 thread
10:37:36 Initializing from normalized Laplacian + noise
10:38:32 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:39:53 Optimization finished
10:40:25 Read 73578 rows and found 13 numeric columns
10:40:25 Using Annoy for neighbor search, n_neighbors = 250
10:40:25 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:40:30 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da1366c7909
10:40:30 Searching Annoy index using 1 thread, search_k = 25000
10:45:35 Annoy recall = 100%
10:45:36 Commencing smooth kNN distance calibration using 1 thread
10:46:05 Initializing from normalized Laplacian + noise
10:47:00 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:48:22 Optimization finished
10:48:25 Read 73578 rows and found 13 numeric columns
10:48:25 Using Annoy for neighbor search, n_neighbors = 250
10:48:25 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:48:30 Writing NN index file to temp file /var/folders/k4/khtkczkd5tn732ftjpwgtr240000gn/T//RtmpFTK9OU/file17da1b7e59c9
10:48:31 Searching Annoy index using 1 thread, search_k = 25000
10:50:48 Annoy recall = 100%
10:50:49 Commencing smooth kNN distance calibration using 1 thread
10:51:17 Initializing from normalized Laplacian + noise
10:52:13 Commencing optimization for 200 epochs, with 14776612 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
10:53:35 Optimization finished

Maybe tSNE works better with this data type than UMAP

#seu <- RunTSNE(seu, dims = 1:10)

DimPlot(seu, reduction = "tsne", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.1")

DimPlot(seu, reduction = "tsne", repel = TRUE, label = TRUE, group.by = "Phenograph.k.271")

NA
NA

# the CHI shows this is the best resolution
DimPlot(seu, reduction = "tsne", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.0.1")

DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.0.1")

DimPlot(seu, reduction = "pca", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.0.1")

library(clustree)

Loading required package: ggraph

clustree(seu, prefix = "RNA_snn_res.") + theme(legend.position = "bottom")

Warning: The `add` argument of `group_by()` is deprecated as of dplyr 1.0.0.
Please use the `.add` argument instead.
This warning is displayed once every 8 hours.
Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.

DimPlot(seu, reduction = "umap", repel = TRUE, label = TRUE, group.by = "RNA_snn_res.1.75")

DoHeatmap(seu, features = allAB, group.by = "RNA_snn_res.1.75")

# save object with more cluster resolutions 

saveRDS(seu,"/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/SeuratfromFlowsomPheno.rds" )

Add cluster annotation from manual annotation for the highest resolution

saveRDS(seu,"/Users/rhalenathomas/Documents/Data/FlowCytometry/PhenoID/Analysis/9MBO/prepro_outsjan20-9000cells/SeuratfromFlowsomPhenoLabels.rds" )